• Journal of Digital Contents Society
• /
• v.15 no.2
• /
• pp.209-217
• /
• 2014

It is very important to classify a lot of table-form documents into the same type of classes or to extract information filled in the template automatically. For these, it is necessary to accurately analyze table-form structure. This paper proposes an algorithm to extract corner points based on line edge segments and to classify the type of junction from table-form images. The algorithm preprocesses image through binarization, skew correction, deletion of isolated small area of black color because that they are probably generated by noises.. And then, it processes detections of edge block, line edges from a edge block, corner points. The extracted corner points are classified as 9 types of junction based on the combination of horizontal/vertical line edge segments in a block. The proposed method is applied to the several unconstraint document images such as tax form, transaction receipt, ordinary document containing tables, etc. The experimental results show that the performance of point detection is over 99%. Considering that almost corner points make a correspondence pair in the table, the information of type of corner and width of line may be useful to analyse the structure of table-form document.

• International Journal of Costume and Fashion
• /
• v.12 no.2
• /
• pp.67-82
• /
• 2012

21st century is the Age of Culture, and a period that is represented by symbolism and imagery. This is no exception for the countries that want to enhance their image in the international community. In order for a country to improve its brand, it has to select a representative emblem, symbols and cultural items. The usual suspects for this are its name, flag, and anthem. Each of these items can elicit different types of symbolism. It can also be used to differentiate the country from others; however, these are not the only sources of symbolism at the country's disposal. Other popular tools include cultural heritage, both tangible and intangible, climate, natural environment, and its national character. A country can use these items to associate itself with certain images. The purpose of this study is to find an objective way to effectively boost Korea's brand. This will be done by comparing and contrasting the ways countries including Korea have used their national emblems to enhance their image. Data from each of the countries were collected and analyzed. The results of this study will become empirical evidence in researches aimed to develop fashion designs that use Korea's national emblem as its motif in order to improve its national brand Countries that were used for this research were United States, United Kingdom, Japan, France and Korea, and they were chosen because their national brand rated highly. The items selected for the analysis were scarves and neckties. This was because, compared to other fashion items, it was easier to sort out scarves and neckties that used motifs of national emblems as well as these two items having the highest usage rate of this type of motif. Group of experts looked through a combined total of 370 scarves and ties and they analyzed the following factors in the design: type of motifs, frequency, use of color, methods of expression and images.

• Journal of the Korean Society of Costume
• /
• v.66 no.1
• /
• pp.135-154
• /
• 2016

The purpose of this study is to research the characteristics and types applied to Korean and foreign luggage brands, and then develop pattern designs for the luggage by applying Korean cultural contents that meet the various fashion needs of travel goods. To select the Korean and foreign luggage brands, a web search was utilized by inputting the keyword, 'luggage brand'. The results, which were extracted from 200 web documents, produced 27 Korean brands and 29 foreign brands that met the requirements. For the data analysis, images and contents were collected through luggage brand websites, and then 927 pattern designs were extracted. The results were as follows. First, characters, figures, animals, and plants were commonly used for the pattern design motifs applied to Korean and foreign luggage. A notable trend was that these motifs were expressed in a stylistic way with a graphic touch. Also, a singular point was formed from the luggage overall, and regularly repeated patterns were very common as well. Secondly, pattern designs for luggage were developed through the application of 'Hangul', 'Hanbok', and 'Hanok'. Nine kinds of patterns were designed via the phases of change into a vector image and color adjustments, and were simulated in luggage design. Adobe Photoshop CS 7.0, and Adobe Illustrator CS 5.0 programs were used for the pattern designs and simulations. This study is meaningful in that it suggested pattern designs for different kinds of luggage in the motifs of Korean cultural contents. It can be used as a useful reference, as we are in a time period where travel goods have become individualized, advanced, and fashionable, as well as laying stress on original design based on cultural interpretation.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.40 no.7
• /
• pp.582-589
• /
• 2012

This paper describes the algorithm recognizing car type from the image received from UAV and the recognition results between three types of car images. Using the NCC(Normalized Cross-Correlation) algorithm, geometric information is matched from template images. Template images are obtained from UAV and satellite map and indoor experiment is performed using satellite map. After verification of the possibility, experiment for verification of same car type recognition is performed using small UAV. In the experiment, same type cars are matched with 0.6 point similarity and truck with similar color distribution is not matched with template image of a sedan.

• The KIPS Transactions:PartB
• /
• v.15B no.3
• /
• pp.205-210
• /
• 2008

A new approach is proposed for restoration of corrupted regions and segmentation in natural text images. The challenge is to fill in the corrupted regions on the basis of color feature analysis by second order symmetric stick tensor. It is show how feature analysis can benefit from analyzing features using tensor voting with chromatic and achromatic components. The proposed method is applied to text images corrupted by manifold types of various noises. Firstly, we decompose an image into chromatic and achromatic components to analyze images. Secondly, selected feature vectors are analyzed by second-order symmetric stick tensor. And tensors are redefined by voting information with neighbor voters, while restore the corrupted regions. Lastly, mode estimation and segmentation are performed by adaptive mean shift and separated clustering method respectively. This approach is automatically done, thereby allowing to easily fill-in corrupted regions containing completely different structures and surrounding backgrounds. Applications of proposed method include the restoration of damaged text images; removal of superimposed noises or streaks. We so can see that proposed approach is efficient and robust in terms of restoring and segmenting text images corrupted.

• Journal of Platform Technology
• /
• v.9 no.3
• /
• pp.63-69
• /
• 2021

Limited materials to make coins for countries and designs suitable for hand-carry make the shape, size, and color of coins similar. This similarity makes that it is difficult for visitors to identify each country's coins. To solve this problem, we propose the coin classification method using CNN effective to image processing. In our coin identification method, we collect the training data by using web crawling and use OpenCV for preprocessing. After preprocessing, we extract features from an image by using three CNN layers and classify coins by using two fully connected network layers. To show that our model designed in this paper is effective for coin classification, we evaluate our model using eight different coin types. From our experimental results, the accuracy for coin classification is about 99.5%.

• Science of Emotion and Sensibility
• /
• v.19 no.3
• /
• pp.3-14
• /
• 2016

This study is aimed to measure the physical colorimetric property according to three conditions, natural dyestuffs (Gardenia, Sappan wood, Lac, Gardenia blue, Mugwort, and Indigo), fabric types (cotton, silk), and presence of mordant (without, with), and then to evaluate the psychological sensibility. Also, to perform analysis of variance (ANOVA) to find out the differences of physical properties according to the three natural dyeing conditions, and to analyze the relationship between physical property and psychological property by Pearson's correlation analysis and then suggest the prediction model by regression analysis using SPSS program (ver. 21.0). Finally, to propose a certain sensibility image map of naturally dyed fabrics, MDS (Multidimensional Scaling) was used, and as a result, Gardenia dyed fabrics having the color sensibilities such as 'hard' and 'heavy' were suggested to evoke masculine image, and to evoke feminine image, Sappan wood and Lac having 'bright', 'transparent', 'soft' and 'light' sensibilities were suggested. Natural image might be induced by using 'subdued' Mugwort dyed fabrics, and active image might be induced by using 'showy' Indigo dyed fabric.

• Smart Media Journal
• /
• v.3 no.4
• /
• pp.28-34
• /
• 2014

Recently the depth-image-based rendering (DIBR) method is usually used in 3D image application filed. Virtual view image is created by using a known view with associated depth map to make a virtual view point which did not taken by the camera. But, disocclusion area occur because the virtual view point is created using a depth image based image 3D warping. To remove those kind of disocclusion region, many hole filling methods are proposed until now. Constant color region searching, horizontal interpolation, horizontal extrapolation, and variational inpainting techniques are proposed as a hole filling methods. But when using those hole filling method some problem occurred. The different types of annoying artifacts are appear in texture region hole filling procedure. In this paper to solve those problem, the multi-directional extrapolation method is newly proposed for efficiency of expanded hole filling performance. The proposed method is efficient when performing hole filling which complex texture background region. Consideration of directionality for hole filling method use the hole neighbor texture pixel value when estimate the hole pixel value. We can check the proposed hole filling method can more efficiently fill the hole region which generated by virtual view synthesis result.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.225-227
• /
• 2022

Now In Seoul, about 75,000 CCTVs are installed in 25 district offices. Each ward office in Seoul has built a control center for CCTV control and is building information such as people, vehicle types, license plate recognition and color classification into big data through 24-hour artificial intelligence intelligent image analysis. Seoul Metropolitan Government has signed MOUs with the Ministry of Land, Infrastructure and Transport, the National Police Agency, the Fire Service, the Ministry of Justice, and the military base to enable rapid response to emergency/emergency situations. In other words, we are building a smart city that is safe and can prevent disasters by providing CCTV images of each ward office. In this paper, the CCTV image is designed to extract the characteristics of the vehicle and personnel when an incident occurs through artificial intelligence, and based on this, predict the escape route and enable continuous tracking. It is designed so that the AI automatically selects and displays the CCTV image of the route. It is designed to expand the smart city integration platform by providing image information and extracted information to the adjacent ward office when the escape route of a person or vehicle related to an incident is expected to an area other than the relevant jurisdiction. This paper will contribute as basic data to the development of smart city integrated platform research.

• Korean Institute of Interior Design Journal
• /
• v.20 no.6
• /
• pp.183-191
• /
• 2011

This study is to set up the appropriate range of observation time through contemplating the characteristics of observation time run for the information acquisition of space. The conclusions reached through this study are as the followings. First, this study could find out that even though the evaluation elements on the three types for image evaluation were the same, the information acquisitions were different as those types varied. On the other hand, the change of the average run-time by type for the information acquisition was found not to be big, in other words, even though the run-time was alike, the information acquisitions varied depending on the type. Second, he evaluation by language media showed the average value by element had the order of [shape>position>number>existence] and the range of their run-time was 94.6~102.9 seconds. The average rate of information acquisition shown at the visual media had the order of [composition>shape>material&color] and the range of run-time was 93.1~99.7 seconds. Third, the evaluation by language media showed that for male subjects the range of information acquisition rate was 39.1~91.4% and that of run-time 85.1~106.0 seconds and for female ones 46.0~94.6% and 96.3~112.3 seconds respectively. In case of the visual media, male subjects showed the range of information acquisition rate was 40.3-66.7% and the range of run-time 82.4~97.9 seconds and the female ones, 42.2~71.0% and 94.0~115.1 seconds respectively, through which we could see that at the evaluation by language media and visual media both the female's range of information acquisition and that of observation time were higher than the male's.